Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Adobe Research Abstract We introduce FaceCam, a system that generates video under customizable camera trajectories for monocular human portrait video input. Recent camera control approaches based on large video-generation models have shown promising progress but often exhibit geometric distortions and visual artifacts on portrait videos due to scale-ambiguous camera representations or
1
0
2
18
Ditch the shaky cams: FaceCam lets you create smooth, customizable portrait videos from a single camera input, sidestepping common 3D reconstruction errors.